[PATCH net-next v15 05/13] rtase: Implement hardware configuration function

[PATCH net-next v15 05/13] rtase: Implement hardware configuration function

[Justin Lai]

Implement rtase_hw_config to set default hardware settings, including
setting interrupt mitigation, tx/rx DMA burst, interframe gap time,
rx packet filter, near fifo threshold and fill descriptor ring and
tally counter address, and enable flow control. When filling the
rx descriptor ring, the first group of queues needs to be processed
separately because the positions of the first group of queues are not
regular with other subsequent groups. The other queues are all newly
added features, but we want to retain the original design. So they were
not put together.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 228 ++++++++++++++++++
 1 file changed, 228 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 1bd4634a8bdb..2337c3cf3cd0 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -466,6 +466,23 @@ static int rtase_init_ring(const struct net_device *dev)
 	return -ENOMEM;
 }
 
+static void rtase_interrupt_mitigation(const struct rtase_private *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++)
+		rtase_w16(tp, RTASE_INT_MITI_TX + i * 2, tp->tx_int_mit);
+
+	for (i = 0; i < tp->func_rx_queue_num; i++)
+		rtase_w16(tp, RTASE_INT_MITI_RX + i * 2, tp->rx_int_mit);
+}
+
+static void rtase_tally_counter_addr_fill(const struct rtase_private *tp)
+{
+	rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(tp->tally_paddr));
+	rtase_w32(tp, RTASE_DTCCR0, lower_32_bits(tp->tally_paddr));
+}
+
 static void rtase_tally_counter_clear(const struct rtase_private *tp)
 {
 	u32 cmd = lower_32_bits(tp->tally_paddr);
@@ -474,6 +491,113 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp)
 	rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_RESET);
 }
 
+static void rtase_desc_addr_fill(const struct rtase_private *tp)
+{
+	const struct rtase_ring *ring;
+	u16 i, cmd, val;
+	int err;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		ring = &tp->tx_ring[i];
+
+		rtase_w32(tp, RTASE_TX_DESC_ADDR0,
+			  lower_32_bits(ring->phy_addr));
+		rtase_w32(tp, RTASE_TX_DESC_ADDR4,
+			  upper_32_bits(ring->phy_addr));
+
+		cmd = i | TX_DESC_CMD_WE | TX_DESC_CMD_CS;
+		rtase_w16(tp, RTASE_TX_DESC_COMMAND, cmd);
+
+		err = read_poll_timeout(rtase_r16, val, !(val & TX_DESC_CMD_CS),
+					10, 1000, false, tp, RTASE_TX_DESC_COMMAND);
+
+		if (err == -ETIMEDOUT)
+			netdev_err(tp->dev, "error occurred in fill tx descriptor\n");
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		ring = &tp->rx_ring[i];
+
+		if (i == 0) {
+			rtase_w32(tp, RTASE_Q0_RX_DESC_ADDR0,
+				  lower_32_bits(ring->phy_addr));
+			rtase_w32(tp, RTASE_Q0_RX_DESC_ADDR4,
+				  upper_32_bits(ring->phy_addr));
+		} else {
+			rtase_w32(tp, (RTASE_Q1_RX_DESC_ADDR0 + ((i - 1) * 8)),
+				  lower_32_bits(ring->phy_addr));
+			rtase_w32(tp, (RTASE_Q1_RX_DESC_ADDR4 + ((i - 1) * 8)),
+				  upper_32_bits(ring->phy_addr));
+		}
+	}
+}
+
+static void rtase_hw_set_features(const struct net_device *dev,
+				  netdev_features_t features)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_config, val;
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	if (features & NETIF_F_RXALL)
+		rx_config |= (ACCEPT_ERR | ACCEPT_RUNT);
+	else
+		rx_config &= ~(ACCEPT_ERR | ACCEPT_RUNT);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config);
+
+	val = rtase_r16(tp, RTASE_CPLUS_CMD);
+	if (features & NETIF_F_RXCSUM)
+		rtase_w16(tp, RTASE_CPLUS_CMD, val | RX_CHKSUM);
+	else
+		rtase_w16(tp, RTASE_CPLUS_CMD, val & ~RX_CHKSUM);
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		rx_config |= (INNER_VLAN_DETAG_EN | OUTER_VLAN_DETAG_EN);
+	else
+		rx_config &= ~(INNER_VLAN_DETAG_EN | OUTER_VLAN_DETAG_EN);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rx_config);
+}
+
+static void rtase_hw_set_rx_packet_filter(struct net_device *dev)
+{
+	u32 mc_filter[2] = { 0xFFFFFFFF, 0xFFFFFFFF };
+	struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_mode;
+
+	rx_mode = rtase_r16(tp, RTASE_RX_CONFIG_0) & ~ACCEPT_MASK;
+	rx_mode |= ACCEPT_BROADCAST | ACCEPT_MYPHYS;
+
+	if (dev->flags & IFF_PROMISC) {
+		rx_mode |= ACCEPT_MULTICAST | ACCEPT_ALLPHYS;
+	} else if (dev->flags & IFF_ALLMULTI) {
+		rx_mode |= ACCEPT_MULTICAST;
+	} else {
+		struct netdev_hw_addr *hw_addr;
+
+		mc_filter[0] = 0;
+		mc_filter[1] = 0;
+
+		netdev_for_each_mc_addr(hw_addr, dev) {
+			u32 bit_nr = eth_hw_addr_crc(hw_addr);
+			u32 idx = u32_get_bits(bit_nr, BIT(31));
+			u32 bit = u32_get_bits(bit_nr, MULTICAST_FILTER_MASK);
+
+			mc_filter[idx] |= BIT(bit);
+			rx_mode |= ACCEPT_MULTICAST;
+		}
+	}
+
+	if (dev->features & NETIF_F_RXALL)
+		rx_mode |= ACCEPT_ERR | ACCEPT_RUNT;
+
+	rtase_w32(tp, RTASE_MAR0, swab32(mc_filter[1]));
+	rtase_w32(tp, RTASE_MAR1, swab32(mc_filter[0]));
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_mode);
+}
+
 static void rtase_irq_dis_and_clear(const struct rtase_private *tp)
 {
 	const struct rtase_int_vector *ivec = &tp->int_vector[0];
@@ -545,6 +669,110 @@ static void rtase_hw_reset(const struct net_device *dev)
 	rtase_nic_reset(dev);
 }
 
+static void rtase_set_rx_queue(const struct rtase_private *tp)
+{
+	u16 reg_data;
+
+	reg_data = rtase_r16(tp, RTASE_FCR);
+	switch (tp->func_rx_queue_num) {
+	case 1:
+		u16p_replace_bits(&reg_data, 0x1, FCR_RXQ_MASK);
+		break;
+	case 2:
+		u16p_replace_bits(&reg_data, 0x2, FCR_RXQ_MASK);
+		break;
+	case 4:
+		u16p_replace_bits(&reg_data, 0x3, FCR_RXQ_MASK);
+		break;
+	}
+	rtase_w16(tp, RTASE_FCR, reg_data);
+}
+
+static void rtase_set_tx_queue(const struct rtase_private *tp)
+{
+	u16 reg_data;
+
+	reg_data = rtase_r16(tp, RTASE_TX_CONFIG_1);
+	switch (tp->tx_queue_ctrl) {
+	case 1:
+		u16p_replace_bits(&reg_data, 0x0, TC_MODE_MASK);
+		break;
+	case 2:
+		u16p_replace_bits(&reg_data, 0x1, TC_MODE_MASK);
+		break;
+	case 3:
+	case 4:
+		u16p_replace_bits(&reg_data, 0x2, TC_MODE_MASK);
+		break;
+	default:
+		u16p_replace_bits(&reg_data, 0x3, TC_MODE_MASK);
+		break;
+	}
+	rtase_w16(tp, RTASE_TX_CONFIG_1, reg_data);
+}
+
+static void rtase_hw_config(struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u32 reg_data32;
+	u16 reg_data16;
+
+	rtase_hw_reset(dev);
+
+	/* set rx dma burst */
+	reg_data16 = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	reg_data16 &= ~(RX_SINGLE_TAG | RX_SINGLE_FETCH);
+	u16p_replace_bits(&reg_data16, RX_DMA_BURST_256, RX_MX_DMA_MASK);
+	rtase_w16(tp, RTASE_RX_CONFIG_0, reg_data16);
+
+	/* new rx descritpor */
+	reg_data16 = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	reg_data16 |= RX_NEW_DESC_FORMAT_EN | PCIE_NEW_FLOW;
+	u16p_replace_bits(&reg_data16, 0xF, RX_MAX_FETCH_DESC_MASK);
+	rtase_w16(tp, RTASE_RX_CONFIG_1, reg_data16);
+
+	rtase_set_rx_queue(tp);
+
+	rtase_interrupt_mitigation(tp);
+
+	/* set tx dma burst size and interframe gap time */
+	reg_data32 = rtase_r32(tp, RTASE_TX_CONFIG_0);
+	u32p_replace_bits(&reg_data32, TX_DMA_BURST_UNLIMITED, TX_DMA_MASK);
+	u32p_replace_bits(&reg_data32, INTERFRAMEGAP, TX_INTER_FRAME_GAP_MASK);
+	rtase_w32(tp, RTASE_TX_CONFIG_0, reg_data32);
+
+	/* new tx descriptor */
+	reg_data16 = rtase_r16(tp, RTASE_TFUN_CTRL);
+	rtase_w16(tp, RTASE_TFUN_CTRL, reg_data16 | TX_NEW_DESC_FORMAT_EN);
+
+	/* tx fetch desc number */
+	rtase_w8(tp, RTASE_TDFNR, 0x10);
+
+	/* tag num select */
+	reg_data16 = rtase_r16(tp, RTASE_MTPS);
+	u16p_replace_bits(&reg_data16, 0x4, TAG_NUM_SEL_MASK);
+	rtase_w16(tp, RTASE_MTPS, reg_data16);
+
+	rtase_set_tx_queue(tp);
+
+	rtase_w16(tp, RTASE_TOKSEL, 0x5555);
+
+	rtase_tally_counter_addr_fill(tp);
+	rtase_desc_addr_fill(tp);
+	rtase_hw_set_features(dev, dev->features);
+
+	/* enable flow control */
+	reg_data16 = rtase_r16(tp, RTASE_CPLUS_CMD);
+	reg_data16 |= (FORCE_TXFLOW_EN | FORCE_RXFLOW_EN);
+	rtase_w16(tp, RTASE_CPLUS_CMD, reg_data16);
+	/* set near fifo threshold - rx missed issue. */
+	rtase_w16(tp, RTASE_RFIFONFULL, 0x190);
+
+	rtase_w16(tp, RTASE_RMS, tp->rx_buf_sz);
+
+	rtase_hw_set_rx_packet_filter(dev);
+}
+
 static void rtase_nic_enable(const struct net_device *dev)
 {
 	const struct rtase_private *tp = netdev_priv(dev);
-- 
2.34.1

[PATCH net-next v15 06/13] rtase: Implement .ndo_start_xmit function

[Justin Lai]

Implement .ndo_start_xmit function to fill the information of the packet
to be transmitted into the tx descriptor, and then the hardware will
transmit the packet using the information in the tx descriptor.
In addition, we also implemented the tx_handler function to enable the
tx descriptor to be reused.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 282 ++++++++++++++++++
 1 file changed, 282 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 2337c3cf3cd0..9bbda3ad0c49 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -252,6 +252,67 @@ static void rtase_mark_to_asic(union rx_desc *desc, u32 rx_buf_sz)
 		   cpu_to_le32(DESC_OWN | eor | rx_buf_sz));
 }
 
+static u32 rtase_tx_avail(struct rtase_ring *ring)
+{
+	return READ_ONCE(ring->dirty_idx) + NUM_DESC - READ_ONCE(ring->cur_idx);
+}
+
+static int tx_handler(struct rtase_ring *ring, int budget)
+{
+	const struct rtase_private *tp = ring->ivec->tp;
+	struct net_device *dev = tp->dev;
+	u32 dirty_tx, tx_left;
+	u32 bytes_compl = 0;
+	u32 pkts_compl = 0;
+	int workdone = 0;
+
+	dirty_tx = ring->dirty_idx;
+	tx_left = READ_ONCE(ring->cur_idx) - dirty_tx;
+
+	while (tx_left > 0) {
+		u32 entry = dirty_tx % NUM_DESC;
+		struct tx_desc *desc = ring->desc +
+				       sizeof(struct tx_desc) * entry;
+		u32 status;
+
+		status = le32_to_cpu(desc->opts1);
+
+		if (status & DESC_OWN)
+			break;
+
+		rtase_unmap_tx_skb(tp->pdev, ring->mis.len[entry], desc);
+		ring->mis.len[entry] = 0;
+		if (ring->skbuff[entry]) {
+			pkts_compl++;
+			bytes_compl += ring->skbuff[entry]->len;
+			napi_consume_skb(ring->skbuff[entry], budget);
+			ring->skbuff[entry] = NULL;
+		}
+
+		dirty_tx++;
+		tx_left--;
+		workdone++;
+
+		if (workdone == RTASE_TX_BUDGET_DEFAULT)
+			break;
+	}
+
+	if (ring->dirty_idx != dirty_tx) {
+		dev_sw_netstats_tx_add(dev, pkts_compl, bytes_compl);
+		WRITE_ONCE(ring->dirty_idx, dirty_tx);
+
+		netif_subqueue_completed_wake(dev, ring->index, pkts_compl,
+					      bytes_compl,
+					      rtase_tx_avail(ring),
+					      RTASE_TX_START_THRS);
+
+		if (ring->cur_idx != dirty_tx)
+			rtase_w8(tp, RTASE_TPPOLL, BIT(ring->index));
+	}
+
+	return 0;
+}
+
 static void rtase_tx_desc_init(struct rtase_private *tp, u16 idx)
 {
 	struct rtase_ring *ring = &tp->tx_ring[idx];
@@ -991,6 +1052,226 @@ static int rtase_close(struct net_device *dev)
 	return 0;
 }
 
+static u32 rtase_tx_vlan_tag(const struct rtase_private *tp,
+			     const struct sk_buff *skb)
+{
+	return (skb_vlan_tag_present(skb)) ?
+		(TX_VLAN_TAG | swab16(skb_vlan_tag_get(skb))) : 0x00;
+}
+
+static u32 rtase_tx_csum(struct sk_buff *skb, const struct net_device *dev)
+{
+	u32 csum_cmd = 0;
+	u8 ip_protocol;
+
+	switch (vlan_get_protocol(skb)) {
+	case htons(ETH_P_IP):
+		csum_cmd = TX_IPCS_C;
+		ip_protocol = ip_hdr(skb)->protocol;
+		break;
+
+	case htons(ETH_P_IPV6):
+		csum_cmd = TX_IPV6F_C;
+		ip_protocol = ipv6_hdr(skb)->nexthdr;
+		break;
+
+	default:
+		ip_protocol = IPPROTO_RAW;
+		break;
+	}
+
+	if (ip_protocol == IPPROTO_TCP)
+		csum_cmd |= TX_TCPCS_C;
+	else if (ip_protocol == IPPROTO_UDP)
+		csum_cmd |= TX_UDPCS_C;
+	else
+		WARN_ON_ONCE(1);
+
+	csum_cmd |= u32_encode_bits(skb_transport_offset(skb), TCPHO_MASK);
+
+	return csum_cmd;
+}
+
+static int rtase_xmit_frags(struct rtase_ring *ring, struct sk_buff *skb,
+			    u32 opts1, u32 opts2)
+{
+	const struct skb_shared_info *info = skb_shinfo(skb);
+	const struct rtase_private *tp = ring->ivec->tp;
+	const u8 nr_frags = info->nr_frags;
+	struct tx_desc *txd = NULL;
+	u32 cur_frag, entry;
+
+	entry = ring->cur_idx;
+	for (cur_frag = 0; cur_frag < nr_frags; cur_frag++) {
+		const skb_frag_t *frag = &info->frags[cur_frag];
+		dma_addr_t mapping;
+		u32 status, len;
+		void *addr;
+
+		entry = (entry + 1) % NUM_DESC;
+
+		txd = ring->desc + sizeof(struct tx_desc) * entry;
+		len = skb_frag_size(frag);
+		addr = skb_frag_address(frag);
+		mapping = dma_map_single(&tp->pdev->dev, addr, len,
+					 DMA_TO_DEVICE);
+
+		if (unlikely(dma_mapping_error(&tp->pdev->dev, mapping))) {
+			if (unlikely(net_ratelimit()))
+				netdev_err(tp->dev,
+					   "Failed to map TX fragments DMA!\n");
+
+			goto err_out;
+		}
+
+		if (((entry + 1) % NUM_DESC) == 0)
+			status = (opts1 | len | RING_END);
+		else
+			status = opts1 | len;
+
+		if (cur_frag == (nr_frags - 1)) {
+			ring->skbuff[entry] = skb;
+			status |= TX_LAST_FRAG;
+		}
+
+		ring->mis.len[entry] = len;
+		txd->addr = cpu_to_le64(mapping);
+		txd->opts2 = cpu_to_le32(opts2);
+
+		/* make sure the operating fields have been updated */
+		wmb();
+		txd->opts1 = cpu_to_le32(status);
+	}
+
+	return cur_frag;
+
+err_out:
+	rtase_tx_clear_range(ring, ring->cur_idx + 1, cur_frag);
+	return -EIO;
+}
+
+static netdev_tx_t rtase_start_xmit(struct sk_buff *skb,
+				    struct net_device *dev)
+{
+	struct skb_shared_info *shinfo = skb_shinfo(skb);
+	struct rtase_private *tp = netdev_priv(dev);
+	u32 q_idx, entry, len, opts1, opts2;
+	struct netdev_queue	*tx_queue;
+	bool stop_queue, door_bell;
+	u32 mss = shinfo->gso_size;
+	struct rtase_ring *ring;
+	struct tx_desc *txd;
+	dma_addr_t mapping;
+	int frags;
+
+	/* multiqueues */
+	q_idx = skb_get_queue_mapping(skb);
+	ring = &tp->tx_ring[q_idx];
+	tx_queue = netdev_get_tx_queue(dev, q_idx);
+
+	if (unlikely(!rtase_tx_avail(ring))) {
+		if (net_ratelimit())
+			netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
+		goto err_stop;
+	}
+
+	entry = ring->cur_idx % NUM_DESC;
+	txd = ring->desc + sizeof(struct tx_desc) * entry;
+
+	opts1 = DESC_OWN;
+	opts2 = rtase_tx_vlan_tag(tp, skb);
+
+	/* tcp segmentation offload (or tcp large send) */
+	if (mss) {
+		if (shinfo->gso_type & SKB_GSO_TCPV4) {
+			opts1 |= GIANT_SEND_V4;
+		} else if (shinfo->gso_type & SKB_GSO_TCPV6) {
+			if (skb_cow_head(skb, 0))
+				goto err_dma_0;
+
+			tcp_v6_gso_csum_prep(skb);
+			opts1 |= GIANT_SEND_V6;
+		} else {
+			WARN_ON_ONCE(1);
+		}
+
+		opts1 |= u32_encode_bits(skb_transport_offset(skb), TCPHO_MASK);
+		opts2 |= u32_encode_bits(mss, MSS_MASK);
+	} else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+		opts2 |= rtase_tx_csum(skb, dev);
+	}
+
+	frags = rtase_xmit_frags(ring, skb, opts1, opts2);
+	if (unlikely(frags < 0))
+		goto err_dma_0;
+
+	if (frags) {
+		len = skb_headlen(skb);
+		opts1 |= TX_FIRST_FRAG;
+	} else {
+		len = skb->len;
+		ring->skbuff[entry] = skb;
+		opts1 |= TX_FIRST_FRAG | TX_LAST_FRAG;
+	}
+
+	if (((entry + 1) % NUM_DESC) == 0)
+		opts1 |= (len | RING_END);
+	else
+		opts1 |= len;
+
+	mapping = dma_map_single(&tp->pdev->dev, skb->data, len,
+				 DMA_TO_DEVICE);
+
+	if (unlikely(dma_mapping_error(&tp->pdev->dev, mapping))) {
+		if (unlikely(net_ratelimit()))
+			netdev_err(dev, "Failed to map TX DMA!\n");
+
+		goto err_dma_1;
+	}
+
+	ring->mis.len[entry] = len;
+	txd->addr = cpu_to_le64(mapping);
+	txd->opts2 = cpu_to_le32(opts2);
+	txd->opts1 = cpu_to_le32(opts1 & ~DESC_OWN);
+
+	/* make sure the operating fields have been updated */
+	wmb();
+
+	door_bell = __netdev_tx_sent_queue(tx_queue, skb->len, netdev_xmit_more());
+
+	txd->opts1 = cpu_to_le32(opts1);
+
+	skb_tx_timestamp(skb);
+
+	/* tx needs to see descriptor changes before updated cur_idx */
+	smp_wmb();
+
+	WRITE_ONCE(ring->cur_idx, ring->cur_idx + frags + 1);
+
+	stop_queue = !netif_subqueue_maybe_stop(dev, ring->index, rtase_tx_avail(ring),
+						RTASE_TX_STOP_THRS,
+						RTASE_TX_START_THRS);
+
+	if (door_bell || stop_queue)
+		rtase_w8(tp, RTASE_TPPOLL, BIT(ring->index));
+
+	return NETDEV_TX_OK;
+
+err_dma_1:
+	ring->skbuff[entry] = NULL;
+	rtase_tx_clear_range(ring, ring->cur_idx + 1, frags);
+
+err_dma_0:
+	dev->stats.tx_dropped++;
+	dev_kfree_skb_any(skb);
+	return NETDEV_TX_OK;
+
+err_stop:
+	netif_stop_queue(dev);
+	dev->stats.tx_dropped++;
+	return NETDEV_TX_BUSY;
+}
+
 static void rtase_enable_eem_write(const struct rtase_private *tp)
 {
 	u8 val;
@@ -1042,6 +1323,7 @@ static void rtase_netpoll(struct net_device *dev)
 static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_open = rtase_open,
 	.ndo_stop = rtase_close,
+	.ndo_start_xmit = rtase_start_xmit,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = rtase_netpoll,
 #endif
-- 
2.34.1

[PATCH net-next v15 07/13] rtase: Implement a function to receive packets

[Justin Lai]

Implement rx_handler to read the information of the rx descriptor,
thereby checking the packet accordingly and storing the packet
in the socket buffer to complete the reception of the packet.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 144 ++++++++++++++++++
 1 file changed, 144 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 9bbda3ad0c49..0a0b456b0f50 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -451,6 +451,150 @@ static void rtase_rx_ring_clear(struct rtase_ring *ring)
 	}
 }
 
+static int rtase_fragmented_frame(u32 status)
+{
+	return (status & (RX_FIRST_FRAG | RX_LAST_FRAG)) !=
+		(RX_FIRST_FRAG | RX_LAST_FRAG);
+}
+
+static void rtase_rx_csum(const struct rtase_private *tp, struct sk_buff *skb,
+			  const union rx_desc *desc)
+{
+	u32 opts2 = le32_to_cpu(desc->desc_status.opts2);
+
+	/* rx csum offload */
+	if (((opts2 & RX_V4F) && !(opts2 & RX_IPF)) || (opts2 & RX_V6F)) {
+		if (((opts2 & RX_TCPT) && !(opts2 & RX_TCPF)) ||
+		    ((opts2 & RX_UDPT) && !(opts2 & RX_UDPF))) {
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		} else {
+			skb->ip_summed = CHECKSUM_NONE;
+		}
+	} else {
+		skb->ip_summed = CHECKSUM_NONE;
+	}
+}
+
+static void rtase_rx_vlan_skb(union rx_desc *desc, struct sk_buff *skb)
+{
+	u32 opts2 = le32_to_cpu(desc->desc_status.opts2);
+
+	if (!(opts2 & RX_VLAN_TAG))
+		return;
+
+	__vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), swab16(opts2 & VLAN_TAG_MASK));
+}
+
+static void rtase_rx_skb(const struct rtase_ring *ring, struct sk_buff *skb)
+{
+	struct rtase_int_vector *ivec = ring->ivec;
+
+	napi_gro_receive(&ivec->napi, skb);
+}
+
+static int rx_handler(struct rtase_ring *ring, int budget)
+{
+	const struct rtase_private *tp = ring->ivec->tp;
+	u32 pkt_size, cur_rx, delta, entry, status;
+	union rx_desc *desc_base = ring->desc;
+	struct net_device *dev = tp->dev;
+	struct sk_buff *skb;
+	union rx_desc *desc;
+	int workdone = 0;
+
+	cur_rx = ring->cur_idx;
+	entry = cur_rx % NUM_DESC;
+	desc = &desc_base[entry];
+
+	do {
+		/* make sure discriptor has been updated */
+		rmb();
+		status = le32_to_cpu(desc->desc_status.opts1);
+
+		if (status & DESC_OWN)
+			break;
+
+		if (unlikely(status & RX_RES)) {
+			if (net_ratelimit())
+				netdev_warn(dev, "Rx ERROR. status = %08x\n",
+					    status);
+
+			dev->stats.rx_errors++;
+
+			if (status & (RX_RWT | RX_RUNT))
+				dev->stats.rx_length_errors++;
+
+			if (status & RX_CRC)
+				dev->stats.rx_crc_errors++;
+
+			if (dev->features & NETIF_F_RXALL)
+				goto process_pkt;
+
+			rtase_mark_to_asic(desc, tp->rx_buf_sz);
+			goto skip_process_pkt;
+		}
+
+process_pkt:
+		pkt_size = status & RX_PKT_SIZE_MASK;
+		if (likely(!(dev->features & NETIF_F_RXFCS)))
+			pkt_size -= ETH_FCS_LEN;
+
+		/* the driver does not support incoming fragmented
+		 * frames. they are seen as a symptom of over-mtu
+		 * sized frames
+		 */
+		if (unlikely(rtase_fragmented_frame(status))) {
+			dev->stats.rx_dropped++;
+			dev->stats.rx_length_errors++;
+			rtase_mark_to_asic(desc, tp->rx_buf_sz);
+			continue;
+		}
+
+		skb = ring->skbuff[entry];
+		dma_sync_single_for_cpu(&tp->pdev->dev,
+					ring->mis.data_phy_addr[entry],
+					tp->rx_buf_sz, DMA_FROM_DEVICE);
+
+		ring->skbuff[entry] = NULL;
+
+		if (dev->features & NETIF_F_RXCSUM)
+			rtase_rx_csum(tp, skb, desc);
+
+		skb->dev = dev;
+		skb_put(skb, pkt_size);
+		skb_mark_for_recycle(skb);
+		skb->protocol = eth_type_trans(skb, dev);
+
+		if (skb->pkt_type == PACKET_MULTICAST)
+			dev->stats.multicast++;
+
+		rtase_rx_vlan_skb(desc, skb);
+		rtase_rx_skb(ring, skb);
+
+		dev_sw_netstats_rx_add(dev, pkt_size);
+
+skip_process_pkt:
+		workdone++;
+		cur_rx++;
+		entry = cur_rx % NUM_DESC;
+		desc = ring->desc + sizeof(union rx_desc) * entry;
+		prefetch(desc);
+	} while (workdone != budget);
+
+	ring->cur_idx = cur_rx;
+	delta = rtase_rx_ring_fill(ring, ring->dirty_idx, ring->cur_idx, 1);
+
+	if (!delta && workdone)
+		netdev_info(dev, "no Rx buffer allocated\n");
+
+	ring->dirty_idx += delta;
+
+	if ((ring->dirty_idx + NUM_DESC) == ring->cur_idx)
+		netdev_emerg(dev, "Rx buffers exhausted\n");
+
+	return workdone;
+}
+
 static void rtase_rx_desc_init(struct rtase_private *tp, u16 idx)
 {
 	struct rtase_ring *ring = &tp->rx_ring[idx];
-- 
2.34.1

[PATCH net-next v15 08/13] rtase: Implement net_device_ops

[Justin Lai]

1. Implement .ndo_set_rx_mode so that the device can change address
list filtering.
2. Implement .ndo_set_mac_address so that mac address can be changed.
3. Implement .ndo_change_mtu so that mtu can be changed.
4. Implement .ndo_tx_timeout to perform related processing when the
transmitter does not make any progress.
5. Implement .ndo_get_stats64 to provide statistics that are called
when the user wants to get network device usage.
6. Implement .ndo_vlan_rx_add_vid to register VLAN ID when the device
supports VLAN filtering.
7. Implement .ndo_vlan_rx_kill_vid to unregister VLAN ID when the device
supports VLAN filtering.
8. Implement the .ndo_setup_tc to enable setting any "tc" scheduler,
classifier or action on dev.
9. Implement .ndo_fix_features enables adjusting requested feature flags
based on device-specific constraints.
10. Implement .ndo_set_features enables updating device configuration to
new features.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 234 ++++++++++++++++++
 1 file changed, 234 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 0a0b456b0f50..16fe3d8e3987 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -1416,6 +1416,11 @@ static netdev_tx_t rtase_start_xmit(struct sk_buff *skb,
 	return NETDEV_TX_BUSY;
 }
 
+static void rtase_set_rx_mode(struct net_device *dev)
+{
+	rtase_hw_set_rx_packet_filter(dev);
+}
+
 static void rtase_enable_eem_write(const struct rtase_private *tp)
 {
 	u8 val;
@@ -1448,6 +1453,202 @@ static void rtase_rar_set(const struct rtase_private *tp, const u8 *addr)
 	rtase_w16(tp, RTASE_LBK_CTRL, LBK_ATLD | LBK_CLR);
 }
 
+static int rtase_set_mac_address(struct net_device *dev, void *p)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	int ret;
+
+	ret = eth_mac_addr(dev, p);
+	if (ret)
+		return ret;
+
+	rtase_rar_set(tp, dev->dev_addr);
+
+	return 0;
+}
+
+static int rtase_change_mtu(struct net_device *dev, int new_mtu)
+{
+	dev->mtu = new_mtu;
+
+	netdev_update_features(dev);
+
+	return 0;
+}
+
+static void rtase_wait_for_quiescence(const struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	struct rtase_int_vector *ivec;
+	u32 i;
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		synchronize_irq(ivec->irq);
+		/* wait for any pending NAPI task to complete */
+		napi_disable(&ivec->napi);
+	}
+
+	rtase_irq_dis_and_clear(tp);
+
+	for (i = 0; i < tp->int_nums; i++) {
+		ivec = &tp->int_vector[i];
+		napi_enable(&ivec->napi);
+	}
+}
+
+static void rtase_sw_reset(struct net_device *dev)
+{
+	struct rtase_private *tp = netdev_priv(dev);
+	int ret;
+
+	netif_stop_queue(dev);
+	netif_carrier_off(dev);
+	rtase_hw_reset(dev);
+
+	/* let's wait a bit while any (async) irq lands on */
+	rtase_wait_for_quiescence(dev);
+	rtase_tx_clear(tp);
+	rtase_rx_clear(tp);
+
+	ret = rtase_init_ring(dev);
+	if (ret) {
+		netdev_err(dev, "unable to init ring\n");
+		rtase_free_desc(tp);
+		return;
+	}
+
+	rtase_hw_config(dev);
+	/* always link, so start to transmit & receive */
+	rtase_hw_start(dev);
+
+	netif_carrier_on(dev);
+	netif_wake_queue(dev);
+}
+
+static void rtase_dump_tally_counter(const struct rtase_private *tp)
+{
+	dma_addr_t paddr = tp->tally_paddr;
+	u32 cmd = lower_32_bits(paddr);
+	u32 val;
+	int err;
+
+	rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(paddr));
+	rtase_w32(tp, RTASE_DTCCR0, cmd);
+	rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_DUMP);
+
+	err = read_poll_timeout(rtase_r32, val, !(val & COUNTER_DUMP), 10, 250,
+				false, tp, RTASE_DTCCR0);
+
+	if (err == -ETIMEDOUT)
+		netdev_err(tp->dev, "error occurred in dump tally counter\n");
+}
+
+static void rtase_dump_state(const struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	int max_reg_size = RTASE_PCI_REGS_SIZE;
+	const struct rtase_counters *counters;
+	const struct rtase_ring *ring;
+	u32 dword_rd;
+	int n = 0;
+
+	ring = &tp->tx_ring[0];
+	netdev_err(dev, "Tx descriptor info:\n");
+	netdev_err(dev, "Tx curIdx = 0x%x\n", ring->cur_idx);
+	netdev_err(dev, "Tx dirtyIdx = 0x%x\n", ring->dirty_idx);
+	netdev_err(dev, "Tx phyAddr = %pad\n", &ring->phy_addr);
+
+	ring = &tp->rx_ring[0];
+	netdev_err(dev, "Rx descriptor info:\n");
+	netdev_err(dev, "Rx curIdx = 0x%x\n", ring->cur_idx);
+	netdev_err(dev, "Rx dirtyIdx = 0x%x\n", ring->dirty_idx);
+	netdev_err(dev, "Rx phyAddr = %pad\n", &ring->phy_addr);
+
+	netdev_err(dev, "Device Registers:\n");
+	netdev_err(dev, "Chip Command = 0x%02x\n", rtase_r8(tp, RTASE_CHIP_CMD));
+	netdev_err(dev, "IMR = %08x\n", rtase_r32(tp, RTASE_IMR0));
+	netdev_err(dev, "ISR = %08x\n", rtase_r32(tp, RTASE_ISR0));
+	netdev_err(dev, "Boot Ctrl Reg(0xE004) = %04x\n",
+		   rtase_r16(tp, RTASE_BOOT_CTL));
+	netdev_err(dev, "EPHY ISR(0xE014) = %04x\n",
+		   rtase_r16(tp, RTASE_EPHY_ISR));
+	netdev_err(dev, "EPHY IMR(0xE016) = %04x\n",
+		   rtase_r16(tp, RTASE_EPHY_IMR));
+	netdev_err(dev, "CLKSW SET REG(0xE018) = %04x\n",
+		   rtase_r16(tp, RTASE_CLKSW_SET));
+
+	netdev_err(dev, "Dump PCI Registers:\n");
+
+	while (n < max_reg_size) {
+		if ((n % RTASE_DWORD_MOD) == 0)
+			netdev_err(tp->dev, "0x%03x:\n", n);
+
+		pci_read_config_dword(tp->pdev, n, &dword_rd);
+		netdev_err(tp->dev, "%08x\n", dword_rd);
+		n += 4;
+	}
+
+	netdev_err(dev, "Dump tally counter:\n");
+	counters = tp->tally_vaddr;
+	rtase_dump_tally_counter(tp);
+
+	netdev_err(dev, "tx_packets %lld\n",
+		   le64_to_cpu(counters->tx_packets));
+	netdev_err(dev, "rx_packets %lld\n",
+		   le64_to_cpu(counters->rx_packets));
+	netdev_err(dev, "tx_errors %lld\n",
+		   le64_to_cpu(counters->tx_errors));
+	netdev_err(dev, "rx_errors %d\n",
+		   le32_to_cpu(counters->rx_errors));
+	netdev_err(dev, "rx_missed %d\n",
+		   le16_to_cpu(counters->rx_missed));
+	netdev_err(dev, "align_errors %d\n",
+		   le16_to_cpu(counters->align_errors));
+	netdev_err(dev, "tx_one_collision %d\n",
+		   le32_to_cpu(counters->tx_one_collision));
+	netdev_err(dev, "tx_multi_collision %d\n",
+		   le32_to_cpu(counters->tx_multi_collision));
+	netdev_err(dev, "rx_unicast %lld\n",
+		   le64_to_cpu(counters->rx_unicast));
+	netdev_err(dev, "rx_broadcast %lld\n",
+		   le64_to_cpu(counters->rx_broadcast));
+	netdev_err(dev, "rx_multicast %d\n",
+		   le32_to_cpu(counters->rx_multicast));
+	netdev_err(dev, "tx_aborted %d\n",
+		   le16_to_cpu(counters->tx_aborted));
+	netdev_err(dev, "tx_underun %d\n",
+		   le16_to_cpu(counters->tx_underun));
+}
+
+static void rtase_tx_timeout(struct net_device *dev, unsigned int txqueue)
+{
+	rtase_dump_state(dev);
+	rtase_sw_reset(dev);
+}
+
+static void rtase_get_stats64(struct net_device *dev,
+			      struct rtnl_link_stats64 *stats)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	const struct rtase_counters *counters = tp->tally_vaddr;
+
+	if (!counters)
+		return;
+
+	netdev_stats_to_stats64(stats, &dev->stats);
+	dev_fetch_sw_netstats(stats, dev->tstats);
+
+	/* fetch additional counter values missing in stats collected by driver
+	 * from tally counter
+	 */
+	rtase_dump_tally_counter(tp);
+	stats->tx_errors = le64_to_cpu(counters->tx_errors);
+	stats->rx_missed_errors = le16_to_cpu(counters->rx_missed);
+	stats->collisions = le32_to_cpu(counters->tx_multi_collision);
+	stats->tx_aborted_errors = le16_to_cpu(counters->tx_aborted);
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /* Polling 'interrupt' - used by things like netconsole to send skbs
  * without having to re-enable interrupts. It's not called while
@@ -1464,13 +1665,46 @@ static void rtase_netpoll(struct net_device *dev)
 }
 #endif
 
+static netdev_features_t rtase_fix_features(struct net_device *dev,
+					    netdev_features_t features)
+{
+	netdev_features_t features_fix = features;
+
+	/*  not support TSO for jumbo frames */
+	if (dev->mtu > ETH_DATA_LEN)
+		features_fix &= ~NETIF_F_ALL_TSO;
+
+	return features_fix;
+}
+
+static int rtase_set_features(struct net_device *dev,
+			      netdev_features_t features)
+{
+	netdev_features_t features_set = features;
+
+	features_set &= NETIF_F_RXALL | NETIF_F_RXCSUM |
+			NETIF_F_HW_VLAN_CTAG_RX;
+
+	if (features_set ^ dev->features)
+		rtase_hw_set_features(dev, features_set);
+
+	return 0;
+}
+
 static const struct net_device_ops rtase_netdev_ops = {
 	.ndo_open = rtase_open,
 	.ndo_stop = rtase_close,
 	.ndo_start_xmit = rtase_start_xmit,
+	.ndo_set_rx_mode = rtase_set_rx_mode,
+	.ndo_set_mac_address = rtase_set_mac_address,
+	.ndo_change_mtu = rtase_change_mtu,
+	.ndo_tx_timeout = rtase_tx_timeout,
+	.ndo_get_stats64 = rtase_get_stats64,
 #ifdef CONFIG_NET_POLL_CONTROLLER
 	.ndo_poll_controller = rtase_netpoll,
 #endif
+	.ndo_fix_features = rtase_fix_features,
+	.ndo_set_features = rtase_set_features,
 };
 
 static void rtase_get_mac_address(struct net_device *dev)
-- 
2.34.1

[PATCH net-next v15 09/13] rtase: Implement pci_driver suspend and resume function

[Justin Lai]

Implement the pci_driver suspend function to enable the device
to sleep, and implement the resume function to enable the device
to resume operation.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 51 +++++++++++++++++++
 1 file changed, 51 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 16fe3d8e3987..b8e5ef489b0c 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -2148,12 +2148,63 @@ static void rtase_shutdown(struct pci_dev *pdev)
 	rtase_reset_interrupt(pdev, tp);
 }
 
+static int rtase_suspend(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+
+	if (netif_running(dev)) {
+		netif_device_detach(dev);
+		rtase_hw_reset(dev);
+	}
+
+	return 0;
+}
+
+static int rtase_resume(struct device *device)
+{
+	struct net_device *dev = dev_get_drvdata(device);
+	struct rtase_private *tp = netdev_priv(dev);
+	int ret;
+
+	/* restore last modified mac address */
+	rtase_rar_set(tp, dev->dev_addr);
+
+	if (!netif_running(dev))
+		goto out;
+
+	rtase_wait_for_quiescence(dev);
+
+	rtase_tx_clear(tp);
+	rtase_rx_clear(tp);
+
+	ret = rtase_init_ring(dev);
+	if (ret) {
+		netdev_err(dev, "unable to init ring\n");
+		rtase_free_desc(tp);
+		return -ENOMEM;
+	}
+
+	rtase_hw_config(dev);
+	/* always link, so start to transmit & receive */
+	rtase_hw_start(dev);
+
+	netif_device_attach(dev);
+out:
+
+	return 0;
+}
+
+static const struct dev_pm_ops rtase_pm_ops = {
+	SYSTEM_SLEEP_PM_OPS(rtase_suspend, rtase_resume)
+};
+
 static struct pci_driver rtase_pci_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = rtase_pci_tbl,
 	.probe = rtase_init_one,
 	.remove = rtase_remove_one,
 	.shutdown = rtase_shutdown,
+	.driver.pm = pm_ptr(&rtase_pm_ops),
 };
 
 module_pci_driver(rtase_pci_driver);
-- 
2.34.1

RE: [PATCH net-next v15 05/13] rtase: Implement hardware configuration function

[Justin Lai]

> -----Original Message-----
> From: Justin Lai <justinlai0215@realtek.com>
> Sent: Friday, January 5, 2024 4:55 PM
> To: kuba@kernel.org
> Cc: davem@davemloft.net; edumazet@google.com; pabeni@redhat.com;
> linux-kernel@vger.kernel.org; netdev@vger.kernel.org; andrew@lunn.ch;
> Ping-Ke Shih <pkshih@realtek.com>; Larry Chiu <larry.chiu@realtek.com>;
> Justin Lai <justinlai0215@realtek.com>
> Subject: [PATCH net-next v15 05/13] rtase: Implement hardware configuration
> function
> 
> Implement rtase_hw_config to set default hardware settings, including setting
> interrupt mitigation, tx/rx DMA burst, interframe gap time, rx packet filter,
> near fifo threshold and fill descriptor ring and tally counter address, and
> enable flow control. When filling the rx descriptor ring, the first group of
> queues needs to be processed separately because the positions of the first
> group of queues are not regular with other subsequent groups. The other
> queues are all newly added features, but we want to retain the original design.
> So they were not put together.
> 
> Signed-off-by: Justin Lai <justinlai0215@realtek.com>
> ---
>  .../net/ethernet/realtek/rtase/rtase_main.c   | 228 ++++++++++++++++++
>  1 file changed, 228 insertions(+)
> 

Sorry, this series of patches has not been sent completely, I will re-send it again.

[PATCH net-next v15 00/13] Add Realtek automotive PCIe driver

[Justin Lai]

This series includes adding realtek automotive ethernet driver 
and adding rtase ethernet driver entry in MAINTAINERS file.

This ethernet device driver for the PCIe interface of 
Realtek Automotive Ethernet Switch,applicable to 
RTL9054, RTL9068, RTL9072, RTL9075, RTL9068, RTL9071.

v1 -> v2:
- Remove redundent debug message.
- Modify coding rule.
- Remove other function codes not related to netdev.

v2 -> v3:
- Remove SR-IOV function - We will add the SR-IOV function together when
uploading the vf driver in the future.
- Remove other unnecessary code and macro.

v3 -> v4:
- Remove function prototype - Our driver does not use recursion, so we
have reordered the code and removed the function prototypes.
- Define macro precisely - Improve macro code readability to make the
source code cleaner.

v4 -> v5:
- Modify ethtool function - Remove some unnecessary code.
- Don't use inline function - Let the compiler decide.

v5 -> v6:
- Some old macro definitions have been removed and replaced with the
lastest usage.
- Replace s32 with int to ensure consistency.
- Clearly point out the objects of the service and remove unnecessary
struct.

v6 -> v7:
- Split this driver into multiple patches.
- Reorganize this driver code and remove redundant code to make this
driver more concise.

v7 -> v8:
- Add the function to calculate time mitigation and the function to 
calculate packet number mitigation. Users can use these two functions 
to calculate the reg value that needs to be set for the mitigation value
they want to set.
- This device is usually used in automotive embedded systems. The page
pool api will use more memory in receiving packets and requires more 
verification, so we currently do not plan to use it in this patch.

v8 -> v9:
- Declare functions that are not extern as static functions and increase
the size of the character array named name in the rtase_int_vector struct
to correct the build warning noticed by the kernel test robot.

v9 -> v10:
- Currently we change to use the page pool api. However, when we allocate
more than one page to an rx buffer, it will cause system errors
in some cases. Therefore, we set the rx buffer to fixed size with 3776
(PAGE_SIZE - SKB_DATA_ALIGN(sizeof(skb_shared_info) )), and the maximum 
value of mtu is set to 3754(rx buffer size - VLAN_ETH_HLEN - ETH_FCS_LEN).
- When ndo_tx_timeout is called, it will dump some device information,
which can be used for debugging.
- When the mtu is greater than 1500, the device supports checksums
but not TSO.
- Fix compiler warnning.

v10 -> v11:
- Added error handling of rtase_init_ring().
- Modify the error related to asymmetric pause in rtase_get_settings.
- Fix compiler error.

v11 -> v12:
- Use pm_sleep_ptr and related macros.
- Remove multicast filter limit.
- Remove VLAN support and CBS offload functions. 
- Remove redundent code.
- Fix compiler warnning.

v12 -> v13:
- Fixed the compiler warning of unuse rtase_suspend() and rtase_resume()
when there is no define CONFIG_PM_SLEEP.

v13 -> v14:
- Remove unuse include.
- call eth_hw_addr_random() to generate random MAC and set device flag 
- use pci_enable_msix_exact() instead of pci_enable_msix_range() 
- If dev->dma_mask is non-NULL, dma_set_mask_and_coherent with a 64-bit
mask will never fail, so remove the part that determines the 32-bit mask.
- set dev->pcpu_stat_type before register_netdev() and core will allocate
stats 
- call NAPI instance at the right location

v14 -> v15:
- In rtase_open, when the request interrupt fails, all request interrupts
are freed.
- When calling netif_device_detach, there is no need to call
netif_stop_queue.
- Call netif_tx_disable() instead of stop_queue(), it takes the tx lock so
there is no need to worry about the packets being transmitted.
- In rtase_tx_handler, napi budget is no longer used, but a customized
tx budget is used.
- Use the start / stop macros from include/net/netdev_queues.h. 
- Remove redundent code.

Justin Lai (13):
  rtase: Add pci table supported in this module
  rtase: Implement the .ndo_open function
  rtase: Implement the rtase_down function
  rtase: Implement the interrupt routine and rtase_poll
  rtase: Implement hardware configuration function
  rtase: Implement .ndo_start_xmit function
  rtase: Implement a function to receive packets
  rtase: Implement net_device_ops
  rtase: Implement pci_driver suspend and resume function
  rtase: Implement ethtool function
  rtase: Add a Makefile in the rtase folder
  realtek: Update the Makefile and Kconfig in the realtek folder
  MAINTAINERS: Add the rtase ethernet driver entry

 MAINTAINERS                                   |    7 +
 drivers/net/ethernet/realtek/Kconfig          |   17 +
 drivers/net/ethernet/realtek/Makefile         |    1 +
 drivers/net/ethernet/realtek/rtase/Makefile   |   10 +
 drivers/net/ethernet/realtek/rtase/rtase.h    |  336 +++
 .../net/ethernet/realtek/rtase/rtase_main.c   | 2314 +++++++++++++++++
 6 files changed, 2685 insertions(+)
 create mode 100644 drivers/net/ethernet/realtek/rtase/Makefile
 create mode 100644 drivers/net/ethernet/realtek/rtase/rtase.h
 create mode 100644 drivers/net/ethernet/realtek/rtase/rtase_main.c

-- 
2.34.1

[PATCH net-next v15 05/13] rtase: Implement hardware configuration function

[Justin Lai]

Implement rtase_hw_config to set default hardware settings, including
setting interrupt mitigation, tx/rx DMA burst, interframe gap time,
rx packet filter, near fifo threshold and fill descriptor ring and
tally counter address, and enable flow control. When filling the
rx descriptor ring, the first group of queues needs to be processed
separately because the positions of the first group of queues are not
regular with other subsequent groups. The other queues are all newly
added features, but we want to retain the original design. So they were
not put together.

Signed-off-by: Justin Lai <justinlai0215@realtek.com>
---
 .../net/ethernet/realtek/rtase/rtase_main.c   | 228 ++++++++++++++++++
 1 file changed, 228 insertions(+)

diff --git a/drivers/net/ethernet/realtek/rtase/rtase_main.c b/drivers/net/ethernet/realtek/rtase/rtase_main.c
index 1bd4634a8bdb..2337c3cf3cd0 100644
--- a/drivers/net/ethernet/realtek/rtase/rtase_main.c
+++ b/drivers/net/ethernet/realtek/rtase/rtase_main.c
@@ -466,6 +466,23 @@ static int rtase_init_ring(const struct net_device *dev)
 	return -ENOMEM;
 }
 
+static void rtase_interrupt_mitigation(const struct rtase_private *tp)
+{
+	u32 i;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++)
+		rtase_w16(tp, RTASE_INT_MITI_TX + i * 2, tp->tx_int_mit);
+
+	for (i = 0; i < tp->func_rx_queue_num; i++)
+		rtase_w16(tp, RTASE_INT_MITI_RX + i * 2, tp->rx_int_mit);
+}
+
+static void rtase_tally_counter_addr_fill(const struct rtase_private *tp)
+{
+	rtase_w32(tp, RTASE_DTCCR4, upper_32_bits(tp->tally_paddr));
+	rtase_w32(tp, RTASE_DTCCR0, lower_32_bits(tp->tally_paddr));
+}
+
 static void rtase_tally_counter_clear(const struct rtase_private *tp)
 {
 	u32 cmd = lower_32_bits(tp->tally_paddr);
@@ -474,6 +491,113 @@ static void rtase_tally_counter_clear(const struct rtase_private *tp)
 	rtase_w32(tp, RTASE_DTCCR0, cmd | COUNTER_RESET);
 }
 
+static void rtase_desc_addr_fill(const struct rtase_private *tp)
+{
+	const struct rtase_ring *ring;
+	u16 i, cmd, val;
+	int err;
+
+	for (i = 0; i < tp->func_tx_queue_num; i++) {
+		ring = &tp->tx_ring[i];
+
+		rtase_w32(tp, RTASE_TX_DESC_ADDR0,
+			  lower_32_bits(ring->phy_addr));
+		rtase_w32(tp, RTASE_TX_DESC_ADDR4,
+			  upper_32_bits(ring->phy_addr));
+
+		cmd = i | TX_DESC_CMD_WE | TX_DESC_CMD_CS;
+		rtase_w16(tp, RTASE_TX_DESC_COMMAND, cmd);
+
+		err = read_poll_timeout(rtase_r16, val, !(val & TX_DESC_CMD_CS),
+					10, 1000, false, tp, RTASE_TX_DESC_COMMAND);
+
+		if (err == -ETIMEDOUT)
+			netdev_err(tp->dev, "error occurred in fill tx descriptor\n");
+	}
+
+	for (i = 0; i < tp->func_rx_queue_num; i++) {
+		ring = &tp->rx_ring[i];
+
+		if (i == 0) {
+			rtase_w32(tp, RTASE_Q0_RX_DESC_ADDR0,
+				  lower_32_bits(ring->phy_addr));
+			rtase_w32(tp, RTASE_Q0_RX_DESC_ADDR4,
+				  upper_32_bits(ring->phy_addr));
+		} else {
+			rtase_w32(tp, (RTASE_Q1_RX_DESC_ADDR0 + ((i - 1) * 8)),
+				  lower_32_bits(ring->phy_addr));
+			rtase_w32(tp, (RTASE_Q1_RX_DESC_ADDR4 + ((i - 1) * 8)),
+				  upper_32_bits(ring->phy_addr));
+		}
+	}
+}
+
+static void rtase_hw_set_features(const struct net_device *dev,
+				  netdev_features_t features)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_config, val;
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	if (features & NETIF_F_RXALL)
+		rx_config |= (ACCEPT_ERR | ACCEPT_RUNT);
+	else
+		rx_config &= ~(ACCEPT_ERR | ACCEPT_RUNT);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_config);
+
+	val = rtase_r16(tp, RTASE_CPLUS_CMD);
+	if (features & NETIF_F_RXCSUM)
+		rtase_w16(tp, RTASE_CPLUS_CMD, val | RX_CHKSUM);
+	else
+		rtase_w16(tp, RTASE_CPLUS_CMD, val & ~RX_CHKSUM);
+
+	rx_config = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	if (dev->features & NETIF_F_HW_VLAN_CTAG_RX)
+		rx_config |= (INNER_VLAN_DETAG_EN | OUTER_VLAN_DETAG_EN);
+	else
+		rx_config &= ~(INNER_VLAN_DETAG_EN | OUTER_VLAN_DETAG_EN);
+
+	rtase_w16(tp, RTASE_RX_CONFIG_1, rx_config);
+}
+
+static void rtase_hw_set_rx_packet_filter(struct net_device *dev)
+{
+	u32 mc_filter[2] = { 0xFFFFFFFF, 0xFFFFFFFF };
+	struct rtase_private *tp = netdev_priv(dev);
+	u16 rx_mode;
+
+	rx_mode = rtase_r16(tp, RTASE_RX_CONFIG_0) & ~ACCEPT_MASK;
+	rx_mode |= ACCEPT_BROADCAST | ACCEPT_MYPHYS;
+
+	if (dev->flags & IFF_PROMISC) {
+		rx_mode |= ACCEPT_MULTICAST | ACCEPT_ALLPHYS;
+	} else if (dev->flags & IFF_ALLMULTI) {
+		rx_mode |= ACCEPT_MULTICAST;
+	} else {
+		struct netdev_hw_addr *hw_addr;
+
+		mc_filter[0] = 0;
+		mc_filter[1] = 0;
+
+		netdev_for_each_mc_addr(hw_addr, dev) {
+			u32 bit_nr = eth_hw_addr_crc(hw_addr);
+			u32 idx = u32_get_bits(bit_nr, BIT(31));
+			u32 bit = u32_get_bits(bit_nr, MULTICAST_FILTER_MASK);
+
+			mc_filter[idx] |= BIT(bit);
+			rx_mode |= ACCEPT_MULTICAST;
+		}
+	}
+
+	if (dev->features & NETIF_F_RXALL)
+		rx_mode |= ACCEPT_ERR | ACCEPT_RUNT;
+
+	rtase_w32(tp, RTASE_MAR0, swab32(mc_filter[1]));
+	rtase_w32(tp, RTASE_MAR1, swab32(mc_filter[0]));
+	rtase_w16(tp, RTASE_RX_CONFIG_0, rx_mode);
+}
+
 static void rtase_irq_dis_and_clear(const struct rtase_private *tp)
 {
 	const struct rtase_int_vector *ivec = &tp->int_vector[0];
@@ -545,6 +669,110 @@ static void rtase_hw_reset(const struct net_device *dev)
 	rtase_nic_reset(dev);
 }
 
+static void rtase_set_rx_queue(const struct rtase_private *tp)
+{
+	u16 reg_data;
+
+	reg_data = rtase_r16(tp, RTASE_FCR);
+	switch (tp->func_rx_queue_num) {
+	case 1:
+		u16p_replace_bits(&reg_data, 0x1, FCR_RXQ_MASK);
+		break;
+	case 2:
+		u16p_replace_bits(&reg_data, 0x2, FCR_RXQ_MASK);
+		break;
+	case 4:
+		u16p_replace_bits(&reg_data, 0x3, FCR_RXQ_MASK);
+		break;
+	}
+	rtase_w16(tp, RTASE_FCR, reg_data);
+}
+
+static void rtase_set_tx_queue(const struct rtase_private *tp)
+{
+	u16 reg_data;
+
+	reg_data = rtase_r16(tp, RTASE_TX_CONFIG_1);
+	switch (tp->tx_queue_ctrl) {
+	case 1:
+		u16p_replace_bits(&reg_data, 0x0, TC_MODE_MASK);
+		break;
+	case 2:
+		u16p_replace_bits(&reg_data, 0x1, TC_MODE_MASK);
+		break;
+	case 3:
+	case 4:
+		u16p_replace_bits(&reg_data, 0x2, TC_MODE_MASK);
+		break;
+	default:
+		u16p_replace_bits(&reg_data, 0x3, TC_MODE_MASK);
+		break;
+	}
+	rtase_w16(tp, RTASE_TX_CONFIG_1, reg_data);
+}
+
+static void rtase_hw_config(struct net_device *dev)
+{
+	const struct rtase_private *tp = netdev_priv(dev);
+	u32 reg_data32;
+	u16 reg_data16;
+
+	rtase_hw_reset(dev);
+
+	/* set rx dma burst */
+	reg_data16 = rtase_r16(tp, RTASE_RX_CONFIG_0);
+	reg_data16 &= ~(RX_SINGLE_TAG | RX_SINGLE_FETCH);
+	u16p_replace_bits(&reg_data16, RX_DMA_BURST_256, RX_MX_DMA_MASK);
+	rtase_w16(tp, RTASE_RX_CONFIG_0, reg_data16);
+
+	/* new rx descritpor */
+	reg_data16 = rtase_r16(tp, RTASE_RX_CONFIG_1);
+	reg_data16 |= RX_NEW_DESC_FORMAT_EN | PCIE_NEW_FLOW;
+	u16p_replace_bits(&reg_data16, 0xF, RX_MAX_FETCH_DESC_MASK);
+	rtase_w16(tp, RTASE_RX_CONFIG_1, reg_data16);
+
+	rtase_set_rx_queue(tp);
+
+	rtase_interrupt_mitigation(tp);
+
+	/* set tx dma burst size and interframe gap time */
+	reg_data32 = rtase_r32(tp, RTASE_TX_CONFIG_0);
+	u32p_replace_bits(&reg_data32, TX_DMA_BURST_UNLIMITED, TX_DMA_MASK);
+	u32p_replace_bits(&reg_data32, INTERFRAMEGAP, TX_INTER_FRAME_GAP_MASK);
+	rtase_w32(tp, RTASE_TX_CONFIG_0, reg_data32);
+
+	/* new tx descriptor */
+	reg_data16 = rtase_r16(tp, RTASE_TFUN_CTRL);
+	rtase_w16(tp, RTASE_TFUN_CTRL, reg_data16 | TX_NEW_DESC_FORMAT_EN);
+
+	/* tx fetch desc number */
+	rtase_w8(tp, RTASE_TDFNR, 0x10);
+
+	/* tag num select */
+	reg_data16 = rtase_r16(tp, RTASE_MTPS);
+	u16p_replace_bits(&reg_data16, 0x4, TAG_NUM_SEL_MASK);
+	rtase_w16(tp, RTASE_MTPS, reg_data16);
+
+	rtase_set_tx_queue(tp);
+
+	rtase_w16(tp, RTASE_TOKSEL, 0x5555);
+
+	rtase_tally_counter_addr_fill(tp);
+	rtase_desc_addr_fill(tp);
+	rtase_hw_set_features(dev, dev->features);
+
+	/* enable flow control */
+	reg_data16 = rtase_r16(tp, RTASE_CPLUS_CMD);
+	reg_data16 |= (FORCE_TXFLOW_EN | FORCE_RXFLOW_EN);
+	rtase_w16(tp, RTASE_CPLUS_CMD, reg_data16);
+	/* set near fifo threshold - rx missed issue. */
+	rtase_w16(tp, RTASE_RFIFONFULL, 0x190);
+
+	rtase_w16(tp, RTASE_RMS, tp->rx_buf_sz);
+
+	rtase_hw_set_rx_packet_filter(dev);
+}
+
 static void rtase_nic_enable(const struct net_device *dev)
 {
 	const struct rtase_private *tp = netdev_priv(dev);
-- 
2.34.1